Search
18 articles for “Hyperparameter Optimization”
-
Automated Machine Learning System for Model Selection and Hyperparameter Optimization
Abstract: The proliferation of machine learning applications in various scientific and industrial domains has given rise to an urgent need for developing principled, automated techniques for optimal architecture selection and hyperparameter tuning for machine learning models without human expert intervention. In this paper, we introduce the Automated Machine Learning System for Model selection and hyperparameter Optimization (AMLSMO)—a state-of-the-art, all-encompassing AutoML system that combines the power of meta-learning-based warm-starting, Bayesian Optimization with …
Published in Recent Trends in Mathematics · Vol. 3, Issue 2, 2026 · pp. 15–23 Read article
-
Comparison of Models of Machine Learning and Hyperparameter optimization methods on various datasets
Abstract: The most likely phase in achieving powerful and robust machine learning models is probably the hyperparameters tuning step. The traditional exhaustive methods of search (Grid Search and others) ensure that the search space is covered, but are computationally very inexpensive; random search is less expensive and can still miss good regions; and lastly, the modern model-based and population-based methods (Bayesian Optimization, Tree-structured Parzen Estimator (TPE), Genetic Algorithms) are thought to …
Published in Recent Trends in Programming languages · Vol. 13, Issue 1, 2026 Read article
-
Particle Swarm Optimization Framework for Accurate Battery State-of-Charge and Remaining Useful Life Estimation
Abstract: Accurate estimation of the State of Charge (SOC) and State of Health (SOH) of a battery is key to safe and efficient management of batteries in electric vehicles and energy-storage systems. However, it is challenging due to high nonlinearity, varying operating conditions, measurement noise, and limited access to comprehensive electrochemical parameters. Traditional data-driven models often generalize poorly and require heavy tuning, which can produce unstable predictions. To address these problems, …
Published in Journal of Automobile Engineering and Applications · Vol. 13, Issue 1, 2026 · pp. 53–64 Read article
-
Predictive Modeling and Optimization of Tensile and Flexural Strength in FDM 3D Printing Using Decision Trees and Bayesian Optimization.
Abstract: This research investigates predictive modelling and optimization technique for the tensile and flexural strength of PlA (Poly Lactic Acid) in Fused Deposition Modelling (FDM) 3D printing. Employing Decision Trees and Bayesian Optimization enhances comprehension and control of 3D printing process. Precise model predicts PLA material properties based on input parameters. Methodology involves rigorous data preprocessing, encompassing, cleaning, transformation, and normalization. Hyperparameter optimization via grid search systematically explores configurations, optimizing model …
Published in Journal of Polymer & Composites · Vol. 11, Issue 12, 2023 · pp. 203–214 Read article
-
Enhanced Multimodal Disease Prediction Using Hybrid Ensemble Learning and AutoML Techniques
Abstract: The integration of hybrid ensemble learning and automated machine learning (AutoML) is revolutionizing disease prediction by addressing the complexity, imbalance, and high dimensionality inherent in medical datasets. This paper proposes an advanced pipeline that combines diverse ensemble learning models with AutoML-based optimization to predict chronic diseases such as kidney diseas-e, Parkinson’s disease, and lung cancer. Publicly available datasets from UCI and PhysioNet repositories were preprocessed using outlier removal, normalization, and …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 1, 2026 Read article
-
Forecasting Commodity Prices Using Deep Learning Techniques: An Empirical Evidence from India
Abstract: Commodity price forecasting is instrumental in financial markets, providing framework for investment choices and risk management practices. Traditional models, including statistical and machine learning approaches, have limitations in capturing the nonlinear and volatile nature of commodity prices. Deep learning (DL) techniques have emerged as promising alternatives, leveraging advanced neural networks to enhance predictive accuracy. This study presents a thorough and comprehensive examination of deep learning applications in commodity price prediction, …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 3, 2025 · pp. 08–12 Read article
-
An Empirical Study of Hyperparameter Impact on Deep Learning Models for Cardamom Leaf Disease Classification
Abstract: Recent advancements in deep learning models like convolutional neural networks and self- attention mechanisms have achieved great success in the field of plant disease classification. This study investigates the efficacy of two pre-trained models, ConvNeXT-Tiny and Swin Transformer-Tiny, for leaf disease classification in cardamom using a publicly available dataset constituting three categories of leaves, namely Healthy, Colletotrichum Blight and Phyllosticta Leaf Spot. The effectiveness of the models highly depends on …
Published in Current Trends in Information Technology · Vol. 15, Issue 3, 2025 · pp. 48–60 Read article
-
Interpretable Skin Cancer Detection via Optimized CNN Models for Smart Healthcare Solutions
Abstract: Skin cancer is a common and potentially life-threatening condition, highlighting the importance of reliable and efficient diagnostic techniques. Recently, convolutional neural networks (CNNs) have demonstrated significant potential in automating the classification of skin cancer using thermoscopic images. Despite these advancements, the lack of interpretability in these models poses a barrier to their widespread use in clinical settings. In this study, we propose an interpretable CNN architecture optimized for skin cancer …
Published in Research & Reviews: A Journal of Bioinformatics · Vol. 12, Issue 1, 2025 · pp. 41–45 Read article
-
Enhancing Wildlife Tourism Management Using Deep Learning and Particle Swarm Optimization (PSO) for Animal Detection in Wildlife Sanctuaries
Abstract: Wildlife tourism is one of the most thriving sectors, faced with huge challenges in terms of safeguarding protected areas. As demand for wildlife experiences accelerates, it becomes necessary to find efficient measures that are friendly to conservation. The use of these advanced techniques in this field such as YOLO and PSO algorithm presents a new dimension on managing wildlife tourism. To harness the abilities of these techniques, this research centers …
Published in Current Trends in Signal Processing · Vol. 14, Issue 3, 2024 · pp. 41–50 Read article
-
Stacked Generalization-Based Deep Learning Approach for Pneumonia Detection
Abstract: The proposed work focuses on a stacked generalization-based approach for diagnosing pneumonia from chest X-ray images. It utilizes regularization, early stopping, and data augmentation to deal with overfitting. It uses safe level SMOTE to deal with class imbalance and attention-based feature fusion to adaptively weigh features based on their importance. It uses two publicly available datasets (RSNA and Kermany) with ground truth provided by expert radiologists. The proposed work used …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 3, 2025 · pp. 20–31 Read article
-
Machine Learning-Based Quantification of Polymer Structure Property Relationships for Predictive Material Design
Abstract: Polymer structures exhibit complex, hierarchical arrangements that strongly influence macroscopic properties, yet consistent quantification remains challenging due to nonlinear interactions and limited unified modeling strategies. Existing approaches inadequately capture generalized structure–property mappings across diverse polymer systems. This research aims to establish a machine learning-based quantification model for polymer structure–property relationships to support predictive material design. A Polymer Structure Property Dataset of 5,000 polymer samples includes structural descriptors and experimentally measured …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 737–754 Read article
-
Implementing Machine Learning in Data Classification
Abstract: Data classification forms an essential aspect of artificial intelligence (AI) and soft computing, helping a great deal in the transformation of raw data into knowledge that forms the basis of numerous applications, such as fraud detection, medical diagnostics, and natural language processing. This study discusses the challenges and the state of the art in data classification, as far as scalability, noise handling, and feature selection optimization are concerned. It gives …
Published in International Journal of Data Structure Studies · Vol. 3, Issue 2, 2025 · pp. 15–22 Read article
-
Handwritten Sanskrit Word Recognition: A Deep Learning Approach Using AlexNet
Abstract: Handwritten Sanskrit word recognition poses significant challenges due to the intricate structure of the script and the considerable variations in handwriting across individuals. To address these challenges, this research introduces a novel methodology employing transfer learning with the AlexNet convolutional neural network. The study utilized two distinct datasets: a specifically curated Sanskrit word image dataset containing 2616 samples, alongside a broader Devanagari character dataset used for validation purposes. The established …
Published in Current Trends in Signal Processing · Vol. 15, Issue 2, 2025 · pp. 33–43 Read article
-
Advancements in Machine Learning: A Comprehensive Review of Algorithms, Applications, and Future Directions
Abstract: Gaining knowledge of Machine learning (ML)-guided format algorithms leverage predictive models to generate novel devices with optimized properties across several domains, which include drug discovery, fabric synthesis, and biomolecular engineering. Selecting an effective format set of policies consists of identifying appropriate hyperparameters, predictive models, and generative mechanisms to maximize format fulfilment. This study introduces an established method for set of policies requirements, ensuring that generated designs meet predefined fulfilment criteria, …
Published in Recent Trends in Programming languages · Vol. 12, Issue 2, 2025 · pp. 17–33 Read article
-
Machine Learning Pipelines: A Survey on Automation, Scalability, and Deployment Strategies
Abstract: Machine learning (ML) has become a critical enabler of intelligent applications across domains, requiring robust, efficient, and scalable deployment workflows. This review paper provides an in-depth overview of machine learning pipelines, emphasizing three key dimensions: automation, scalability, and deployment methodologies. It begins by exploring automation techniques that reduce manual effort in data ingestion, preprocessing, model selection, and hyperparameter tuning. Tools such as AutoML, TFX, and workflow orchestration platforms are examined …
Published in Journal of Advances in Shell Programming · Vol. 12, Issue 2, 2025 · pp. 17–28 Read article
-
Mechanical Strength Prediction of Nano-Silica Concrete Composites Using Machine Learning Techniques
Abstract: Nano-silica, or nanosilica, refers to silicon dioxide nanoparticles, which are a kind of silica (SiO₂) with diameters that often fall below 100 nanometers. This nanomaterial has attracted considerable attention because of its distinctive characteristics and diverse array of uses, notably in augmenting the performance of materials such as concrete. The integration of nanoparticles with cementitious matrix in nano-silica concrete offers a viable approach to improving the mechanical characteristics and longevity …
Published in Journal of Polymer & Composites · Vol. 13, Issue 1, 2025 · pp. 963–973 Read article
-
Machine Learning Assisted Design and Analysis of Polymer Composite Materials for Sustainable Renewable Energy Systems
Abstract: Accurate prediction and optimization of polymer composite properties is of paramount importance in the design of these lightweight, durable, and sustainable materials within renewable energy technologies. This work will provide a holistic machine learning-assisted framework that unites materials informatics with domain-specific features and state-of-the-art ML methodologies in the prediction of the mechanical properties of polymer composites, such as tensile strength. This includes embedding several ensemble models, including Random Forest and …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 391–402 Read article
-
Prediction of Mechanical Properties for Advanced Engineering Applications utilizing Polymer Composite Materials by Machine Learning
Abstract: Polymer composites show great promise as engineering materials because of their mechanical performance, resistance to corrosion, lightweight nature, and adaptability in design. Aerospace, automotive, biomedical, maritime, and civil engineers all rely on mechanical property prediction to cut down on trial expenses, expedite product development, and optimize material selection. Speedy design optimization is not possible using traditional numerical and experimental methods due to the high costs associated with material characterisation, computational …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 Read article